From 7a1b959646c45a81d3495148b1fa6c2da585eb59 Mon Sep 17 00:00:00 2001
From: Austin-Olacsi <138650713+Austin-Olacsi@users.noreply.github.com>
Date: Mon, 10 Nov 2025 09:27:00 -0700
Subject: [PATCH] [fix] hackernews contains HTML escape codes

---
 searx/engines/hackernews.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/searx/engines/hackernews.py b/searx/engines/hackernews.py
index 3b0dd2d87..8ee20f7d2 100644
--- a/searx/engines/hackernews.py
+++ b/searx/engines/hackernews.py
@@ -6,6 +6,7 @@ from urllib.parse import urlencode
 from dateutil.relativedelta import relativedelta
 
 from flask_babel import gettext
+from searx.utils import html_to_text
 
 # Engine metadata
 about = {
@@ -75,6 +76,7 @@ def response(resp):
         object_id = hit["objectID"]
         points = hit.get("points") or 0
         num_comments = hit.get("num_comments") or 0
+        content = hit.get("url") or html_to_text(hit.get("comment_text")) or html_to_text(hit.get("story_text"))
 
         metadata = ""
         if points != 0 or num_comments != 0:
@@ -83,7 +85,7 @@ def response(resp):
             {
                 "title": hit.get("title") or f"{gettext('author')}: {hit['author']}",
                 "url": f"https://news.ycombinator.com/item?id={object_id}",
-                "content": hit.get("url") or hit.get("comment_text") or hit.get("story_text") or "",
+                "content": content,
                 "metadata": metadata,
                 "author": hit["author"],
                 "publishedDate": datetime.fromtimestamp(hit["created_at_i"]),